Recursive Markov Decision Processes and Recursive Stochastic Games.
Kousha EtessamiMihalis YannakakisPublished in: J. ACM (2015)
Keyphrases
- markov decision processes
- stochastic games
- average reward
- state space
- reinforcement learning algorithms
- finite state
- reinforcement learning
- optimal policy
- dynamic programming
- finite horizon
- policy iteration
- multiagent reinforcement learning
- action space
- markov decision process
- average cost
- partially observable
- infinite horizon
- nash equilibria
- single agent
- function approximation